Legal claims defining the scope of protection, as filed with the USPTO.
1. A processing system, comprising: sequencer circuitry for initiating a plurality of processing stages of first, second and third instructions, said second instruction being an execution serialized instruction; execution circuitry coupled to said sequencer circuitry; and dispatch circuitry coupled to said execution circuitry for: finishing a dispatch processing stage of said first instruction so that said first instruction is dispatched to said execution circuitry; in response to finishing said dispatch processing stage of said first instruction, finishing a dispatch processing stage of a second instruction so that said second instruction is dispatched to said execution circuitry; and in response to finishing said dispatch processing stage of said second instruction, finishing a dispatch processing stage of a third instruction so that said third instruction is dispatched to said execution circuitry; and said execution circuitry being operable to reorder an execution sequence of said first, second and third instructions subsequent to said first, second and third instructions being dispatched to said execution circuitry and to initiate an execution processing stage of said dispatched third instruction prior to initiating an execution processing stage of said dispatched second instruction.
2. The system of claim 1 wherein said execution circuitry is operable to: initiate an execution processing stage of said dispatched first instruction; and in response to finishing said execution processing stage of said first instruction, initiate said execution processing stage of said dispatched second instruction.
3. The system of claim 1 wherein said execution circuitry comprises at least one reservation station, and said dispatch circuitry is operable to finish said dispatch processing stage of said second instruction so that said second instruction is dispatched to said reservation station.
4. The system of claim 1 wherein said sequencer circuitry is operable to output an indication to said execution circuitry to inhibit said execution processing stage of said dispatched second instruction.
5. The system of claim 4 wherein: said execution circuitry is operable to initiate an execution processing stage of said dispatched first instruction; said sequencer circuitry is operable to output an additional indication in response to said execution circuitry finishing said execution processing stage of said first instruction; and said execution circuitry is operable to initiate said execution processing stage of said dispatched second instruction in response to said additional indication.
6. The system of claim 1 wherein said second instruction is to be executed non-speculatively.
7. The system of claim 6 wherein a result of said execution processing stage of said second instruction is to be written directly to a storage location without intermediate storage in a rename buffer.
8. The system of claim 1 wherein said execution circuitry is operable to: initiate an execution processing stage of said dispatched first instruction; and in response to finishing said execution processing stage of said first instruction, initiate said execution processing stage of said dispatched second instruction after all its source operand information is available and valid.
9. The system of claim 8 wherein said second instruction specifies at least one unforwarded source operand.
10. The system of claim 1 wherein said execution circuitry comprises: first execution circuitry for executing said first instruction; and second execution circuitry for executing said second instruction.
11. The system of claim 1 wherein said execution circuitry comprises: first execution circuitry for executing said third instruction; and second execution circuitry for executing said second instruction.
12. The system of claim 1 wherein said dispatch circuitry is integral with said sequencer circuitry.
13. A method of operating a processing system, comprising the steps of: initiating a plurality of processing stages of first, second and third instructions, said second instruction being an execution serialized instruction; finishing a dispatch processing stage of said first instruction so that said first instruction is dispatched to execution circuitry; in response to finishing said dispatch processing stage of said first instruction, finishing a dispatch processing stage of a second instruction so that said second instruction is dispatched to said execution circuitry; in response to finishing said dispatch processing stage of said second instruction, finishing a dispatch processing stage of a third instruction so that said third instruction is dispatched to said execution circuitry; and reordering an execution sequence of said first, second and third instructions subsequent to said first, second and third instructions being dispatched to said execution circuitry and initiating an execution processing stage of said dispatched third instruction prior to initiating an execution processing stage of said dispatched second instruction.
14. The method of claim 13 and further comprising the steps of: initiating an execution processing stage of said dispatched first instruction; and in response to finishing said execution processing stage of said first instruction, initiating said execution processing stage of said dispatched second instruction.
15. The method of claim 13 wherein said step of finishing said dispatch processing stage of said second instruction comprises the step of finishing said dispatch processing stage of said second instruction so that said second instruction is dispatched to a reservation station of said execution circuitry.
16. The method of claim 13 wherein said step of finishing said dispatch processing stage of said second instruction comprises the step of outputting an indication to said execution circuitry to inhibit said execution processing stage of said dispatched second instruction.
17. The method of claim 16 and further comprising the steps of: initiating an execution processing stage of said dispatched first instruction; and in response to finishing said execution processing stage of said first instruction, outputting an additional indication to said execution circuitry to initiate said execution processing stage of said dispatched second instruction.
18. The method of claim 13 wherein said second instruction is to be executed non-speculatively.
19. The method of claim 18 wherein a result of said execution processing stage of said second instruction is to be written directly to a storage location without intermediate storage in a rename buffer.
20. The method of claim 13 and further comprising the steps of: initiating an execution processing stage of said dispatched first instruction; and in response to finishing said execution processing stage of said first instruction, initiating said execution processing stage of said dispatched second instruction after all its source operand information is available and valid.
21. The method of claim 20 wherein said second instruction specifies at least one unforwarded source operand.
Complete technical specification and implementation details from the patent document.
DETAILED DESCRIPTION
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
Unknown
March 21, 2000
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.